Skip to main content
Glama

whale-data

by com.coinlobster
OverviewDiscussionsAdmin

Near-live price bars

price_candles
Read-onlyIdempotent

Near-live price bars (OHLCV) for a pair: interval "1h" (default) or "1d", oldest first, each bar { t, o, h, l, c, v }. This is the lane a bot reads to compute its OWN indicators (moving averages, momentum, whatever it wants), so CoinLobster does not need to ship them. NEAR-LIVE and separate on purpose from market_history, which is the daily archive that settles days behind: every reply carries newest_candle_age_min and stale so a live lane is never confused with a stopped one. Keyless covers the free pairs up to 24 bars; a paid plan covers every streamed pair up to 720 bars (asking for more returns the cap and says so in capped). The newest bar is still forming. Descriptive market data only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
coinNoAlias for pair.
pairNoTrading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. On the free plans BTC answers in full and any other coin as a headline; a paid plan reaches every streamed pair. A pair this server does not stream comes back covered:false.
limitNoHow many bars, newest-ending. Capped at 24 on the free plans and 720 on a paid plan; asking for more returns the cap, and the payload says so in `capped`.
intervalNoBar length: "1h" (default) or "1d". Anything else is read as 1h.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
noteNoOne line saying what the numbers cover, or why there are none. Read it before reporting any zero as a market reading.
pairNoThe pair these candles are for.
as_ofNoThe time of the newest bar, in milliseconds.
countNoHow many rows this reply carries.
staleNoTrue only when the newest bar is older than a live lane explains. When true the numbers are stopped, not the current price.
cappedNoPresent only when an argument was cut down to a ceiling. Absent means nothing was clamped, so a smaller number than you asked for is the data and not a limit.
candlesNoThe bars, oldest first, each { t, o, h, l, c, v }: time, open, high, low, close and volume. The newest bar is still forming. This is the NEAR-LIVE lane, not the days-behind daily archive that market_history reads.
coveredNoFalse when this server does not stream the pair at all. No plan adds it.
intervalNo1h or 1d. The bar length each candle covers.
availableNoFalse when this lane could not answer: a producer is dark, the pair sits outside this plan, or the argument named something we do not carry. Absent or true means the numbers are a real reading, not a guess.
free_pairsNoThe pairs a keyless connection can read, returned when the pair asked for is not one of them.
stale_noteNoPresent when stale is true: how far past live the newest bar has fallen.
access_noteNoWhat this connection could not return and what lifts it. Always pass this on to the user: it is the only place that information appears.
newest_candle_age_minNoHow many minutes old the newest bar is, so a live lane can be told from a stopped one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"How many bars, newest-ending. Capped at 168 keyless and 720 on a paid plan; asking for more returns the cap, and the payload says so in `capped`."New value: +"How many bars, newest-ending. Capped at 24 on the free plans and 720 on a paid plan; asking for more returns the cap, and the payload says so in `capped`."
    • changedInput schema / properties / pair / description
      Previous value: -"Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. Keyless calls reach the free pairs only; a paid plan reaches every streamed pair. A pair this server does not stream comes back covered:false."New value: +"Trading pair, for example ETH/USD. A bare symbol like ETH is read as ETH/USD. Defaults to BTC/USD when omitted. On the free plans BTC answers in full and any other coin as a headline; a paid plan reaches every streamed pair. A pair this server does not stream comes back covered:false."
  2. Added

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the read-only/idempotent annotations, the description discloses meaningful runtime behavior: NEAR-LIVE data, newest_candle_age_min and stale fields, newest bar still forming, free/paid bar caps, and the capped field. This is exactly the kind of context annotations alone do not provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence earns its place: purpose and shape, intended use case, differentiation from the archive, live-vs-stale signals, plan limits, and final caveats. The key identity is front-loaded in the first sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema, annotations, and 100% schema coverage, the description covers almost everything an agent needs: what the endpoint returns, why to choose it, how it differs from market_history, availability limits, and reliability signals. There are no material gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; the schema already fully documents coin, pair, limit, and interval. The description reinforces the interval default and cap behavior but does not add significant new parameter-level semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: near-live OHLCV price bars for a pair, with interval, ordering, and bar shape. It explicitly contrasts itself with market_history, so an agent can distinguish it from sibling tools without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says this is the lane a bot reads to compute its own indicators, and that it is deliberately separate from market_history, which settles days behind. This gives an agent an explicit 'when to use this vs that' rule and also signals that this is descriptive data, not an action tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All whale-data toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources